Risk Analysis of Accident Severities on Freeway Based on Copula Bayesian Network

Abstract

Preventing severe injuries in crashes has emerged as a central concern in freeway traffic safety research. To mitigate severe injuries, it is essential that the influential factors affecting accident severity be identified. In this research, accident data were collected from Los Angeles County, California, USA, freeways in the years 2016–2019, aggregating five influencing factors from five perspectives, including temporal factors, environmental factors, accident factors, accident participant factors, and traffic factors. A copula Bayesian network modeling approach was developed which combines a Bayesian network with a copula function to depict the interrelationships among crash severity outcomes and various influencing factors. The approach has the following advantages: (1) It has a more reasonable and interpretable structure. (2) It makes up for the limitation of traditional Bayesian networks that can only analyze discrete features by enabling the handling of both discrete and continuous variables. The copula Bayesian network reasoning analysis further demonstrates that various interconnections exist among different factors, and that accident type, lighting conditions, alcohol involvement, and average occupancy are the most critical contributors to fatal or severe injury accidents.